© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26711
    Prev
    Next
    INDEX
    Explanations

    question or scientific measurement

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects NMR spectroscopy nucleus–frequency labels (e.g. “1H,” “13C,” “31P”) and their associated numeric values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    その
    -1.24
     desmotiv
    -1.16
    |}{\
    -1.14
    picious
    -1.12
     nové
    -1.09
     Spanyol
    -1.09
    Zubereitung
    -1.08
     jejich
    -1.08
     Accesorios
    -1.08
     Início
    -1.05
    POSITIVE LOGITS
    uxedo
    1.09
     these
    1.06
    を楽しむ
    1.05
    шных
    0.99
    Hilsen
    0.98
    ريقيا
    0.97
    のカ
    0.97
    รวจ
    0.96
     Nutr
    0.94
    quée
    0.92
    Activations Density 0.000%

    No Known Activations